{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T12:55:02Z","timestamp":1742993702426,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030557539"},{"type":"electronic","value":"9783030557546"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-55754-6_7","type":"book-chapter","created":{"date-parts":[[2020,8,9]],"date-time":"2020-08-09T23:02:37Z","timestamp":1597014157000},"page":"115-132","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Strengthening Deterministic Policies for POMDPs"],"prefix":"10.1007","author":[{"given":"Leonore","family":"Winterer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ralf","family":"Wimmer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nils","family":"Jansen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bernd","family":"Becker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,8,10]]},"reference":[{"issue":"3","key":"7_CR1","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/s10458-009-9103-z","volume":"21","author":"C Amato","year":"2010","unstructured":"Amato, C., Bernstein, D.S., Zilberstein, S.: Optimizing fixed-size stochastic controllers for POMDPs and decentralized POMDPs. Auton. Agent. Multi-Agent Syst. 21(3), 293\u2013320 (2010). https:\/\/doi.org\/10.1007\/s10458-009-9103-z","journal-title":"Auton. Agent. Multi-Agent Syst."},{"key":"7_CR2","unstructured":"Aras, R., Dutech, A., Charpillet, F.: Mixed integer linear programming for exact finite-horizon planning in decentralized POMDPs. In: ICAPS, pp. 18\u201325. AAAI (2007). http:\/\/www.aaai.org\/Library\/ICAPS\/2007\/icaps07-003.php"},{"key":"7_CR3","doi-asserted-by":"publisher","unstructured":"Baier, C., Dubslaff, C., Kl\u00fcppelholz, S.: Trade-off analysis meets probabilistic model checking. In: CSL-LICS, pp. 1:1\u20131:10. ACM (2014). https:\/\/doi.org\/10.1145\/2603088.2603089","DOI":"10.1145\/2603088.2603089"},{"key":"7_CR4","volume-title":"Principles of Model Checking","author":"C Baier","year":"2008","unstructured":"Baier, C., Katoen, J.P.: Principles of Model Checking. MIT Press, Cambridge (2008)"},{"key":"7_CR5","unstructured":"Braziunas, D.: POMDP Solution Methods. University of Toronto (2003)"},{"key":"7_CR6","doi-asserted-by":"publisher","unstructured":"Brock, O., Trinkle, J., Ramos, F.: SARSOP: Efficient point-based POMDP planning by approximating optimally reachable belief spaces. In: Robotics: Science and Systems IV. MIT Press (2009). https:\/\/doi.org\/10.15607\/RSS.2008.IV.009","DOI":"10.15607\/RSS.2008.IV.009"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Carr, S., Jansen, N., Wimmer, R., Serban, A.C., Becker, B., Topcu, U.: Counterexample-guided strategy improvement for POMDPs using recurrent neural networks. In: IJCAI, pp. 5532\u20135539. ijcai.org (2019)","DOI":"10.24963\/ijcai.2019\/768"},{"key":"7_CR8","doi-asserted-by":"publisher","unstructured":"Chatterjee, K., Chmel\u00edk, M., Gupta, R., Kanodia, A.: Qualitative analysis of POMDPs with temporal logic specifications for robotics applications. In: ICRA, pp. 325\u2013330 (2015). https:\/\/doi.org\/10.1109\/ICRA.2015.7139019","DOI":"10.1109\/ICRA.2015.7139019"},{"key":"7_CR9","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.artint.2016.01.007","volume":"234","author":"K Chatterjee","year":"2016","unstructured":"Chatterjee, K., Chmel\u00edk, M., Gupta, R., Kanodia, A.: Optimal cost almost-sure reachability in POMDPs. Artif. Intell. 234, 26\u201348 (2016). https:\/\/doi.org\/10.1016\/j.artint.2016.01.007","journal-title":"Artif. Intell."},{"key":"7_CR10","doi-asserted-by":"publisher","unstructured":"Chatterjee, K., De Alfaro, L., Henzinger, T.A.: Trading memory for randomness. In: QEST. IEEE (2004). https:\/\/doi.org\/10.1109\/QEST.2004.1348035","DOI":"10.1109\/QEST.2004.1348035"},{"key":"7_CR11","unstructured":"Chrisman, L.: Reinforcement learning with perceptual aliasing: the perceptual distinctions approach. In: AAAI, pp. 183\u2013188. AAAI Press\/The MIT Press (1992)"},{"key":"7_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/978-3-662-54580-5_8","volume-title":"Tools and Algorithms for the Construction and Analysis of Systems","author":"M Cubuktepe","year":"2017","unstructured":"Cubuktepe, M., Jansen, N., Junges, S., Katoen, J.-P., Papusha, I., Poonawala, H.A., Topcu, U.: Sequential convex programming for the efficient verification of parametric MDPs. In: Legay, A., Margaria, T. (eds.) TACAS 2017. LNCS, vol. 10206, pp. 133\u2013150. Springer, Heidelberg (2017). https:\/\/doi.org\/10.1007\/978-3-662-54580-5_8"},{"key":"7_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1007\/978-3-030-01090-4_10","volume-title":"Automated Technology for Verification and Analysis","author":"M Cubuktepe","year":"2018","unstructured":"Cubuktepe, M., Jansen, N., Junges, S., Katoen, J.-P., Topcu, U.: Synthesis in pMDPs: a tale of 1001 parameters. In: Lahiri, S.K., Wang, C. (eds.) ATVA 2018. LNCS, vol. 11138, pp. 160\u2013176. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01090-4_10"},{"key":"7_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1007\/978-3-319-11936-6_11","volume-title":"Automated Technology for Verification and Analysis","author":"C Dehnert","year":"2014","unstructured":"Dehnert, C., Jansen, N., Wimmer, R., \u00c1brah\u00e1m, E., Katoen, J.-P.: Fast debugging of PRISM models. In: Cassez, F., Raskin, J.-F. (eds.) ATVA 2014. LNCS, vol. 8837, pp. 146\u2013162. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-11936-6_11"},{"key":"7_CR15","doi-asserted-by":"publisher","unstructured":"Etessami, K., Kwiatkowska, M.Z., Vardi, M.Y., Yannakakis, M.: Multi-objective model checking of Markov decision processes. Logical Methods Comput. Sci. 4(4) (2008). https:\/\/doi.org\/10.2168\/LMCS-4(4:8)2008","DOI":"10.2168\/LMCS-4(4:8)2008"},{"issue":"1\u20132","key":"7_CR16","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1016\/S0004-3702(02)00376-4","volume":"147","author":"R Givan","year":"2003","unstructured":"Givan, R., Dean, T.L., Greig, M.: Equivalence notions and model minimization in Markov decision processes. Artif. Intell. 147(1\u20132), 163\u2013223 (2003)","journal-title":"Artif. Intell."},{"key":"7_CR17","unstructured":"Gurobi Optimization, LLC: Gurobi optimizer reference manual (2019). http:\/\/www.gurobi.com"},{"issue":"16","key":"7_CR18","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1016\/j.ifacol.2018.08.046","volume":"51","author":"S Haesaert","year":"2018","unstructured":"Haesaert, S., Nilsson, P., Vasile, C.I., Thakker, R., Agha-mohammadi, A., Ames, A.D., Murray, R.M.: Temporal logic control of POMDPs via label-based stochastic simulation relations. IFAC-PapersOnLine 51(16), 271\u2013276 (2018). In: ADHS","journal-title":"IFAC-PapersOnLine"},{"issue":"1","key":"7_CR19","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s10009-010-0146-x","volume":"13","author":"EM Hahn","year":"2010","unstructured":"Hahn, E.M., Hermanns, H., Zhang, L.: Probabilistic reachability for parametric Markov models. Softw. Tools Technol. Transfer 13(1), 3\u201319 (2010)","journal-title":"Softw. Tools Technol. Transfer"},{"key":"7_CR20","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1613\/jair.678","volume":"13","author":"M Hauskrecht","year":"2000","unstructured":"Hauskrecht, M.: Value-function approximations for partially observable Markov decision processes. J. Artif. Intell. Res. 13, 33\u201394 (2000)","journal-title":"J. Artif. Intell. Res."},{"key":"7_CR21","unstructured":"Junges, S., et al.: Parameter synthesis for Markov models. CoRR abs\/1903.07993 (2019)"},{"key":"7_CR22","unstructured":"Junges, S., Jansen, N., Wimmer, R., Quatmann, T., Winterer, L., Katoen, J., Becker, B.: Finite-state controllers of POMDPs using parameter synthesis. In: UAI, pp. 519\u2013529. AUAI Press (2018)"},{"issue":"1","key":"7_CR23","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/S0004-3702(98)00023-X","volume":"101","author":"LP Kaelbling","year":"1998","unstructured":"Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and acting in partially observable stochastic domains. Artif. Intell. 101(1), 99\u2013134 (1998)","journal-title":"Artif. Intell."},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Kumar, A., Mostafa, H., Zilberstein, S.: Dual formulations for optimizing Dec-POMDP controllers. In: ICAPS, pp. 202\u2013210. AAAI Press (2016)","DOI":"10.1609\/icaps.v26i1.13759"},{"key":"7_CR25","unstructured":"Littman, M.L., Topcu, U., Fu, J., Isbell, C., Wen, M., MacGlashan, J.: Environment-independent task specifications via GLTL. arXiv preprint 1704.04341 (2017)"},{"key":"7_CR26","unstructured":"Madani, O., Hanks, S., Condon, A.: On the undecidability of probabilistic planning and infinite-horizon partially observable Markov decision problems. In: AAAI, pp. 541\u2013548. AAAI Press (1999)"},{"key":"7_CR27","unstructured":"Meuleau, N., Peshkin, L., Kim, K.E., Kaelbling, L.P.: Learning finite-state controllers for partially observable environments. In: UAI, pp. 427\u2013436. Morgan Kaufmann (1999)"},{"issue":"3","key":"7_CR28","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1007\/s11241-017-9269-4","volume":"53","author":"G Norman","year":"2017","unstructured":"Norman, G., Parker, D., Zou, X.: Verification and control of partially observable probabilistic systems. Real-Time Syst. 53(3), 354\u2013402 (2017)","journal-title":"Real-Time Syst."},{"issue":"3","key":"7_CR29","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1287\/moor.12.3.441","volume":"12","author":"CH Papadimitriou","year":"1987","unstructured":"Papadimitriou, C.H., Tsitsiklis, J.N.: The complexity of Markov decision processes. Math. Oper. Res. 12(3), 441\u2013450 (1987)","journal-title":"Math. Oper. Res."},{"key":"7_CR30","unstructured":"Pineau, J., Gordon, G., Thrun, S.: Point-based value iteration: an anytime algorithm for POMDPs. In: IJCAI, pp. 1025\u20131032. Morgan Kaufmann (2003)"},{"key":"7_CR31","doi-asserted-by":"publisher","unstructured":"Pnueli, A.: The temporal logic of programs. In: FOCS, pp. 46\u201357. IEEE Computer Society (1977). https:\/\/doi.org\/10.1109\/SFCS.1977.32","DOI":"10.1109\/SFCS.1977.32"},{"key":"7_CR32","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley Series in Probability and Statistics, Wiley-Interscience (2005)"},{"key":"7_CR33","unstructured":"Russell, S.J., Norvig, P.: Artificial Intelligence - A Modern Approach (3. internat. ed.). Pearson Education (2010)"},{"key":"7_CR34","volume-title":"Theory of Linear and Integer Programming","author":"A Schrijver","year":"1999","unstructured":"Schrijver, A.: Theory of Linear and Integer Programming. Wiley, Hoboken (1999)"},{"issue":"1","key":"7_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10458-012-9200-2","volume":"27","author":"G Shani","year":"2013","unstructured":"Shani, G., Pineau, J., Kaplow, R.: A survey of point-based POMDP solvers. Auton. Agents Multi-Agent Syst. 27(1), 1\u201351 (2013)","journal-title":"Auton. Agents Multi-Agent Syst."},{"key":"7_CR36","unstructured":"Silver, D., Veness, J.: Monte-carlo planning in large pomdps. In: Lafferty, J.D., Williams, C.K.I., Shawe-Taylor, J., Zemel, R.S., Culotta, A. (eds.) NIPS, pp. 2164\u20132172. Curran Associates, Inc. (2010)"},{"key":"7_CR37","volume-title":"Probabilistic Robotics","author":"S Thrun","year":"2005","unstructured":"Thrun, S., Burgard, W., Fox, D.: Probabilistic Robotics. The MIT Press, Cambridge (2005)"},{"key":"7_CR38","doi-asserted-by":"publisher","unstructured":"Velasquez, A.: Steady-state policy synthesis for verifiable control. In: Kraus, S. (ed.) IJCAI, pp. 5653\u20135661. ijcai.org (2019). https:\/\/doi.org\/10.24963\/ijcai.2019\/784","DOI":"10.24963\/ijcai.2019\/784"},{"issue":"4","key":"7_CR39","doi-asserted-by":"publisher","first-page":"12:1","DOI":"10.1145\/2382559.2382563","volume":"4","author":"N Vlassis","year":"2012","unstructured":"Vlassis, N., Littman, M.L., Barber, D.: On the computational complexity of stochastic controller optimization in POMDPs. ACM Trans. Comput. Theory 4(4), 12:1\u201312:8 (2012). https:\/\/doi.org\/10.1145\/2382559.2382563","journal-title":"ACM Trans. Comput. Theory"},{"key":"7_CR40","unstructured":"Wang, Y., Chaudhuri, S., Kavraki, L.E.: Bounded policy synthesis for POMDPs with safe-reachability objectives. In: AAMAS, pp. 238\u2013246. Int\u2019l Foundation for Autonomous Agents and Multiagent Systems Richland, SC, USA\/ACM (2018)"},{"key":"7_CR41","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.tcs.2014.06.020","volume":"549","author":"R Wimmer","year":"2014","unstructured":"Wimmer, R., Jansen, N., \u00c1brah\u00e1m, E., Katoen, J.P., Becker, B.: Minimal counterexamples for linear-time probabilistic verification. Theor. Comput. Sci. 549, 61\u2013100 (2014). https:\/\/doi.org\/10.1016\/j.tcs.2014.06.020","journal-title":"Theor. Comput. Sci."},{"key":"7_CR42","doi-asserted-by":"crossref","unstructured":"Winterer, L., et al.: Motion planning under partial observability using game-based abstraction. In: CDC, pp. 2201\u20132208. IEEE (2017)","DOI":"10.1109\/CDC.2017.8263971"},{"key":"7_CR43","doi-asserted-by":"crossref","unstructured":"Wongpiromsarn, T., Frazzoli, E.: Control of probabilistic systems under dynamic, partially known environments with temporal logic specifications. In: CDC, pp. 7644\u20137651. IEEE (2012)","DOI":"10.1109\/CDC.2012.6426524"}],"container-title":["Lecture Notes in Computer Science","NASA Formal Methods"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-55754-6_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,6]],"date-time":"2022-11-06T09:30:06Z","timestamp":1667727006000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-55754-6_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030557539","9783030557546"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-55754-6_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"10 August 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NFM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"NASA Formal Methods Symposium","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Moffett Field, CA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 May 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 May 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nfm2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ti.arc.nasa.gov\/events\/nfm-2020\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"62","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"20","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"32% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}